arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1807.08230cs.CL
收藏

基于分类器集成的德语方言识别

German Dialect Identification Using Classifier Ensembles

University of Bucharest(布加勒斯特大学);Harvard Medical School(哈佛医学院)

Alina Maria Ciobanu, Shervin Malmasi, Liviu P. Dinu

摘要:

在本文中,我们将GDI_classification条目介绍给在2018年VarDial评估活动范围内组织的第二个德语方言识别(GDI)共享任务。我们提出了一个基于SVM分类器集成训练的字符和单词的系统。该系统的培训上收集的五个瑞士德语方言的组织者提供的语音转录。数据集中的记录包括来自巴塞尔、伯尔尼、卢塞恩和苏黎世的演讲者。我们的挑战赛进入达到62.03%的F1分数,并在八支球队中排名第三。

英文摘要:

In this paper we present the GDI_classification entry to the second German Dialect Identification (GDI) shared task organized within the scope of the VarDial Evaluation Campaign 2018. We present a system based on SVM classifier ensembles trained on characters and words. The system was trained on a collection of speech transcripts of five Swiss-German dialects provided by the organizers. The transcripts included in the dataset contained speakers from Basel, Bern, Lucerne, and Zurich. Our entry in the challenge reached 62.03% F1-score and was ranked third out of eight teams.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑